| { |
| "best_metric": null, |
| "best_model_checkpoint": null, |
| "epoch": 1.839738348323794, |
| "eval_steps": 500, |
| "global_step": 4500, |
| "is_hyper_param_search": false, |
| "is_local_process_zero": true, |
| "is_world_process_zero": true, |
| "log_history": [ |
| { |
| "epoch": 0.2, |
| "learning_rate": 2.795584627964023e-05, |
| "loss": 2.2019, |
| "step": 500 |
| }, |
| { |
| "epoch": 0.41, |
| "learning_rate": 2.591169255928046e-05, |
| "loss": 1.9636, |
| "step": 1000 |
| }, |
| { |
| "epoch": 0.61, |
| "learning_rate": 2.3867538838920688e-05, |
| "loss": 1.9246, |
| "step": 1500 |
| }, |
| { |
| "epoch": 0.82, |
| "learning_rate": 2.1823385118560917e-05, |
| "loss": 1.8572, |
| "step": 2000 |
| }, |
| { |
| "epoch": 1.02, |
| "learning_rate": 1.9779231398201146e-05, |
| "loss": 1.7804, |
| "step": 2500 |
| }, |
| { |
| "epoch": 1.23, |
| "learning_rate": 1.7735077677841375e-05, |
| "loss": 1.5332, |
| "step": 3000 |
| }, |
| { |
| "epoch": 1.43, |
| "learning_rate": 1.56909239574816e-05, |
| "loss": 1.5243, |
| "step": 3500 |
| }, |
| { |
| "epoch": 1.64, |
| "learning_rate": 1.3646770237121831e-05, |
| "loss": 1.5248, |
| "step": 4000 |
| }, |
| { |
| "epoch": 1.84, |
| "learning_rate": 1.160261651676206e-05, |
| "loss": 1.5064, |
| "step": 4500 |
| } |
| ], |
| "logging_steps": 500, |
| "max_steps": 7338, |
| "num_train_epochs": 3, |
| "save_steps": 500, |
| "total_flos": 1.0581146839835136e+16, |
| "trial_name": null, |
| "trial_params": null |
| } |
|
|
